Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Resistance
    -0.07
     Remarks
    -0.07
    Expand
    -0.07
    conditionally
    -0.07
    핑
    -0.06
    manifest
    -0.06
    	LCD
    -0.06
     UB
    -0.06
    bing
    -0.06
     취
    -0.06
    POSITIVE LOGITS
    (This
    0.07
    .scheduler
    0.06
    (Item
    0.06
     Lyon
    0.06
    正在
    0.06
     тому
    0.06
     though
    0.06
    頁
    0.06
     تجهیزات
    0.06
     uğra
    0.06
    Act Density 0.004%

    No Known Activations